Data storytelling meets interpretable machine learning: Decoding AI decisions for non-experts without revealing sensitive data and model details

Making AI decisions understandable to everyone matters: The research demonstrates that when AI explanations are presented as data stories rather than technical visualizations, non-experts find them significantly more comprehensible—76.4% of respondents rated "What-if" stories as more understandable than traditional SHAP visualizations, showing that accessibility to AI decisions shouldn't be limited to technical experts.

Data storytelling can protect privacy while explaining decisions: The study introduces a "data desensitization" approach that allows organizations to explain why an AI system made a particular decision without revealing sensitive personal information or proprietary model details, addressing a key tension between transparency and privacy in responsible AI deployment.

Structured narratives improve AI explainability: Using a simple "And-But-Therefore" (ABT) narrative structure to explain AI decisions—combined with "What-if" and "Why-not" scenarios—provides a practical framework that helps non-experts understand both what an AI system decided and why it made that choice, making accountability more achievable in real-world applications.

Technical complexity shouldn't be a barrier to AI accountability: The research validates that combining interpretable machine learning tools (like SHAP values) with storytelling techniques can bridge the gap between sophisticated AI systems and public understanding, suggesting that responsible AI governance requires communication strategies, not just better algorithms.